DSCI is a self-hosted CI server that uses an LLM-based agent to automatically generate pipeline configurations. Users can request pipelines by describing their project requirements (e.g., Python with pytest and coverage), and the system generates ready-to-use pipeline code within a minute.
System One Lite is a local LLM project that converts language models into typed decision engines, eliminating free-form text generation in favor of direct probability scores for predefined options. It runs on Apple silicon using open-weight models and returns structured answers without generated tokens, designed for routing, ranking, and classification tasks in software systems.
PlanLint is an open-source AEC compliance checker that uses LLMs only for entity recognition and text parsing, while delegating all compliance verdicts to deterministic Python logic grounded in actual CAD geometry and codebook rules. The system models compliance as a bipartite graph in Neo4j, ingesting architectural drawings through specialized pipelines for different sheet types and applying rule-based verification to prevent AI hallucinations that could pass non-compliant designs.
ImpactGate is a merge gate tool that measures and gates structural decay introduced by code changes using a complexity-based impact formula. It runs as a CLI, pre-commit hook, or CI plugin (GitHub, GitLab, Jenkins) and can warn or block changes exceeding configurable thresholds based on absolute scores or percentile rankings.
Cloudflare's default security settings inadvertently blocked legitimate API clients using Python and Perl libraries, returning 403 errors before payment terms could be presented. The company identified seven configuration issues including Browser Integrity Check, Bot Fight Mode, and AI Crawl Control that prevented paying agents from accessing their paid API endpoints across all three zones.
A developer rebooted a 2010s community calendar aggregation project using LLM assistance to combine public event calendars from organizations via iCalendar feeds. The new implementation leveraged Claude and ChatGPT to rapidly solve technical challenges including timezone normalization and built a static HTML calendar renderer using Jinja2 templates without external dependencies.
A programmer defends YAML against common criticisms, arguing that many complained-about issues stem from improper usage rather than the specification itself. The author shares experiences with YAML in projects like a Discord bot and Space Station 14, noting that explicit deserialization logic prevents problems like implicit type conversion.
never-again is a tool that prevents AI coding agents from repeating fixed bugs by automatically creating git hooks or adding rules to a file. It runs locally without accounts or tracking, works on macOS, Linux, WSL, and Windows, and requires git, bash, and Python 3.7+.